Dynamic cache row fail accumulation due to catastrophic failure

Abstract

A technique is provided for accumulating failures. A failure of a first row is detected in a group of array macros, the first row having first row address values. A mask has mask bits corresponding to each of the first row address values. The mask bits are initially in active status. A failure of a second row, having second row address values, is detected. When none of the first row address values matches the second row address values, and when mask bits are all in the active status, the array macros are determined to be bad. When at least one of the first row address values matches the second row address values, mask bits that correspond to at least one of the first row address values that match are kept in active status, and mask bits that correspond to non-matching first address values are set to inactive status.

What is claimed is: 
     
       1. A method by a cache controller for taking a wordline offline based on errors, the method comprising:
 reading, by the cache controller, the wordline in a cache, wherein the wordline is utilized to read a plurality of ECC words in the cache; 
 in response to reading the wordline, detecting, by the cache controller, errors on the wordline; 
 in response to detecting the errors, determining, by the cache controller, that the wordline is a bad wordline to be taken offline based on the wordline comprising at least one of the conditions:
 one ECC word having an uncorrectable error and another ECC word having a correctable error; and 
 one certain ECC word having the correctable error and another certain ECC word having the correctable error; 
 
 when the wordline comprises the at least one of the conditions to be the bad wordline, the cache controller is configured to at least one of:
 store a bad wordline address of the bad wordline such that any future reference to the bad wordline is flagged as the uncorrectable error, 
 cause a dynamic or static repair of the bad wordline, 
 fence off any wordlines having had the uncorrectable error detected, and 
 perform calling home in order to have the bad wordline ticketed for repair; 
 
 monitoring, by the cache controller, future accesses to the cache, thereby allowing the cache controller to cover multiple fail modes; 
 finding, by the cache controller, adjacent wordlines in the cache that have wordline addresses matching portions of the bad wordline address of the bad wordline; and 
 marking, by the cache controller, the adjacent wordlines as bad wordlines.